A novel sparse filtering approach based on time-frequency feature extraction and softmax regression for intelligent fault diagnosis under different speeds

Modern agricultural mechanization has put forward higher requirements for the intelligent defect diagnosis. However, the fault features are usually learned and classified under all speeds without considering the effects of speed fluctuation. To overcome this deficiency, a novel intelligent defect detection framework based on time-frequency transformation is presented in this work. In the framework, the samples under one speed are employed for training sparse filtering model, and the remaining samples under different speeds are adopted for testing the effectiveness. Our proposed approach contains two stages: 1) the time-frequency domain signals are acquired from the mechanical raw vibration data by the short time Fourier transform algorithm, and then the defect features are extracted from time-frequency domain signals by sparse filtering algorithm; 2) different defect types are classified by the softmax regression using the defect features. The proposed approach can be employed to mine available fault characteristics adaptively and is an effective intelligent method for fault detection of agricultural equipment. The fault detection performances confirm that our approach not only owns strong ability for fault classification under different speeds, but also obtains higher identification accuracy than the other methods.